@pipeworx/epo-ops

Connect: https://gateway.pipeworx.io/epo-ops/mcp · Install: one-click buttons

Tools: 5

European Patent Office Open Patent Services MCP — published patents from the EPO worldwide patent register (DocDB).

Tools

  • search_patents(query, range?) — CQL search against published patents
  • get_biblio(number, format?) — bibliographic data
  • get_family(number) — INPADOC family (related applications worldwide)
  • get_abstract(number) — abstract text
  • get_claims(number) — claims text

Auth

  • Platform key: gateway env PLATFORM_EPO_KEY (consumer_key:consumer_secret pair joined with colon)
  • BYO: ?_apiKey=<consumer_key>:<consumer_secret> after registering at https://developers.epo.org/

The pack exchanges credentials for a bearer token (20-min TTL, cached).

Data source

https://ops.epo.org/3.2/rest-services/ — OAuth2 client_credentials, JSON via Accept: application/json.

Patent number formats: EPO docdb (EP.1234567.A1), epodoc (EP1234567), original (EP1234567B1).

Tools

  • search_patents — Search published patents using CQL (EPO Common Query Language). Returns a paginated list of publication numbers matching the query. Example queries: “ta=hydrogen”, “in=Tesla”, “pa=apple”, “txt=neural
  • get_biblio — Bibliographic data for a patent — title, inventors, applicants, dates, classifications.
  • get_family — INPADOC family — related patent applications worldwide for the same underlying invention.
  • get_abstract — Abstract text for a patent.
  • get_claims — Claims text for a patent.

Tools

  • get_abstract — Abstract text for a patent.
  • get_biblio — Bibliographic data for a patent — title, inventors, applicants, dates, classifications.
  • get_claims — Claims text for a patent.
  • get_family — INPADOC family — related patent applications worldwide for the same underlying invention.
  • search_patents — Search published patents using CQL (EPO Common Query Language). Returns a paginated list of publication numbers matching the query. Example queries: ta=hydrogen , in=Tesla , pa=apple , txt=neural netw

Regenerated from source · build May 21, 2026